JSON documents are everywhere on the Internet. Servers spend a lot of time parsing these documents. We want to accelerate the parsing of JSON per se using commonly available SIMD instructions as much as possible while doing full validation (including character encoding). This library is part of the [Awesome Modern C++](https://awesomecpp.com) list.
We also have an informal [blog post providing some background and context](https://branchfree.org/2019/02/25/paper-parsing-gigabytes-of-json-per-second/).
simdjson uses three-quarters less instructions than state-of-the-art parser RapidJSON and fifty percent less than sajson. To our knowledge, simdjson is the first fully-validating JSON parser to run at gigabytes per second on commodity processors.
- AVX2 (i.e., Intel processors starting with the Haswell microarchitecture released 2013 and AMD processors starting with the Zen microarchitecture released 2017),
- or SSE 4.2 and CLMUL (i.e., Intel processors going back to Westmere released in 2010 or AMD processors starting with the Jaguar used in the PS4 and XBox One)
- or a 64-bit ARM processor (ARMv8-A): this covers a wide range of mobile processors, including all Apple processors currently available for sale, going as far back as the iPhone 5s (2013).
Under Windows, we build some tools using the windows/dirent_portable.h file (which is outside our library code): it under the liberal (business-friendly) MIT license.
On Intel and AMD processors, we get best performance by using the hardware support for AVX2 instructions. However, simdjson also runs on older Intel and AMD processors. We require a minimum feature support of SSE 4.2 and CLMUL (2010 Intel Westmere or better). The code automatically detects the feature set of your processor and switches to the right function at runtime (a technique sometimes called runtime dispatch).
On x64 hardware, you should typically build your code by specifying the oldest/less-featureful system you want to support so that runtime dispatch may work. The minimum requirement for simdjson is the equivalent of a Westmere processor (SSE 4.2 and PCLMUL). If you build your code by asking the compiler to use more advanced instructions (e.g., `-mavx2`, `/AVX2` or `-march=haswell`), then it will break runtime dispatch and your binaries will fail to run on older processors.
The simdjson library is mostly single-threaded. Thread safety is the responsability of the caller: it is unsafe to reuse a ParsedJson object between different threads.
If you are on an x64 processor, the runtime dispatching assigns the right code path the first time that parsing is attempted. The runtime dispatching is thread-safe.
The json stream parser is threaded, using exactly two threads.
If you are processing large files (e.g., 100 MB), it is likely that the performance of simdjson will be limited by page misses and/or page allocation. [On some systems, memory allocation runs far slower than we can parse (e.g., 1.4GB/s).](https://lemire.me/blog/2020/01/14/how-fast-can-you-allocate-a-large-block-of-memory-in-c/)
You will get best performance with large or huge pages. Under Linux, you can enable transparent huge pages with a command like `echo always > /sys/kernel/mm/transparent_hugepage/enabled` (root access may be required). We recommend that you report performance numbers with and without huge pages.
Another strategy is to reuse pre-allocated buffers. That is, you avoid reallocating memory. You just allocate memory once and reuse the blocks of memory.
The main API involves populating a `ParsedJson` object which hosts a fully navigable document-object-model (DOM) view of the JSON document. The DOM can be accessed using [JSON Pointer](https://tools.ietf.org/html/rfc6901) paths, for example. The main function is `json_parse` which takes a string containing the JSON document as well as a reference to pre-allocated `ParsedJson` object (which can be reused multiple time). Once you have populated the `ParsedJson` object you can navigate through the DOM with an iterator (e.g., created by `ParsedJson::Iterator pjh(pj)`, see 'Navigating the parsed document').
Though the `padded_string` class is recommended for best performance, you can call `json_parse` and `build_parsed_json`, passing a standard `std::string` object.
As needed, the `json_parse` and `build_parsed_json` functions copy the input data to a temporary buffer readable up to SIMDJSON_PADDING bytes beyond the end of the data.
The simdjson library also support multithreaded JSON streaming through a large file containing many smaller JSON documents in either [ndjson](http://ndjson.org) or [JSON lines](http://jsonlines.org) format. We support files larger than 4GB.
You need a recent compiler like clang or gcc. We recommend at least GNU GCC/G++ 7 or LLVM clang 6. For example, you can install a recent compiler with brew:
Optional: You need to tell cmake which compiler you wish to use by setting the CC and CXX variables. Under bash, you can do so with commands such as `export CC=gcc-7` and `export CXX=g++-7`.
We assume you have a common 64-bit Windows PC with at least Visual Studio 2017 and an x64 processor with AVX2 support (2013 Intel Haswell or later) or SSE 4.2 + CLMUL (2010 Westmere or later).
- Install [CMake](https://cmake.org/download/). When you install it, make sure to ask that `cmake` be made available from the command line. Please choose a recent version of cmake.
- Create a subdirectory within simdjson, such as `VisualStudio`.
- Using a shell, go to this newly created directory.
- Type `cmake -DCMAKE_GENERATOR_PLATFORM=x64 ..` in the shell while in the `VisualStudio` repository. (Alternatively, if you want to build a DLL, you may use the command line `cmake -DCMAKE_GENERATOR_PLATFORM=x64 -DSIMDJSON_BUILD_STATIC=OFF ..`.)
- This last command (`cmake ...`) created a Visual Studio solution file in the newly created directory (e.g., `simdjson.sln`). Open this file in Visual Studio. You should now be able to build the project and run the tests. For example, in the `Solution Explorer` window (available from the `View` menu), right-click `ALL_BUILD` and select `Build`. To test the code, still in the `Solution Explorer` window, select `RUN_TESTS` and select `Build`.
[vcpkg](https://github.com/Microsoft/vcpkg) users on Windows, Linux and macOS can download and install `simdjson` with one single command from their favorite shell.
will build and install `simdjson` as a static library.
On Windows (64-bit):
```
.\vcpkg.exe install simdjson:x64-windows
```
will build and install `simdjson` as a shared library.
```
.\vcpkg.exe install simdjson:x64-windows-static
```
will build and install `simdjson` as a static library.
These commands will also print out instructions on how to use the library from MSBuild or CMake-based projects.
If you find the version of `simdjson` shipped with `vcpkg` is out-of-date, feel free to report it to `vcpkg` community either by submiting an issue or by creating a PR.
-`json2json -d mydoc.json` parses the document, constructs a model and then dumps model (as a tape) to standard output. The tape format is described in the accompanying file `tape.md`.
-`minify mydoc.json` minifies the JSON document, outputting the result to standard output. Minifying means to remove the unneeded white space characters.
-`jsonpointer mydoc.json <jsonpath> <jsonpath> ... <jsonpath>` parses the document, constructs a model and then processes a series of [JSON Pointer paths](https://tools.ietf.org/html/rfc6901). The result is itself a JSON document.
- We support UTF-8 (and thus ASCII), nothing else (no Latin, no UTF-16). We do not believe this is a genuine limitation, because we do not think there is any serious application that needs to process JSON data without an ASCII or UTF-8 encoding. If the UTF-8 contains a leading BOM, it should be omitted: the user is responsible for detecting and skipping the BOM; UTF-8 BOMs are discouraged.
- All strings in the JSON document may have up to 4294967295 bytes in UTF-8 (4GB). To enforce this constraint, we refuse to parse a document that contains more than 4294967295 bytes (4GB). This should accommodate most JSON documents.
- Performance is optimized for JSON documents spanning at least a tens kilobytes up to many megabytes: the performance issues with having to parse many tiny JSON documents or one truly enormous JSON document are different.
_We do not aim to provide a general-purpose JSON library._ A library like RapidJSON offers much more than just parsing, it helps you generate JSON and offers various other convenient functions. We merely parse the document.
- We parse integers and floating-point numbers as separate types which allows us to support large signed 64-bit integers in [-9223372036854775808,9223372036854775808), like a Java `long` or a C/C++ `long long` and large unsigned integers up to the value 18446744073709551615. Among the parsers that differentiate between integers and floating-point numbers, not all support 64-bit integers. (For example, sajson rejects JSON files with integers larger than or equal to 2147483648. RapidJSON will parse a file containing an overly long integer like 18446744073709551616 as a floating-point number.) When we cannot represent exactly an integer as a signed or unsigned 64-bit value, we reject the JSON document.
- We support the full range of 64-bit floating-point numbers (binary64). The values range from ` std::numeric_limits<double>::lowest()` to `std::numeric_limits<double>::max()`, so from -1.7976e308 all the way to 1.7975e308. Extreme values (less or equal to -1e308, greater or equal to 1e308) are rejected: we refuse to parse the input document.
- We test for accurate float parsing with a bound on the [unit of least precision (ULP)](https://en.wikipedia.org/wiki/Unit_in_the_last_place) of one. Practically speaking, this implies 15 digits of accuracy or better.
- We do full UTF-8 validation as part of the parsing. (Parsers like fastjson, gason and dropbox json11 do not do UTF-8 validation. The sajson parser does incomplete UTF-8 validation, accepting code point
- We fully validate the white-space characters outside of the strings. Parsers like RapidJSON will accept JSON documents with null characters outside of strings.
- Stage 1. (Find marks) Identifies quickly structure elements, strings, and so forth. We validate UTF-8 encoding at that stage.
- Stage 2. (Structure building) Involves constructing a "tree" of sort (materialized as a tape) to navigate through the data. Strings and numbers are parsed at this stage.
From a `simdjson::ParsedJson` instance, you can create an iterator (of type `simdjson::ParsedJson::Iterator` which is in fact `simdjson::ParsedJson::BasicIterator<DEFAULT_MAX_DEPTH>` ) via a constructor:
```
ParsedJson::Iterator pjh(pj); // pj is a ParsedJSON
```
You then have access to the following methods on the resulting `simdjson::ParsedJson::Iterator` instance:
*`bool is_ok() const`: whether you have a valid iterator, will be false if your parent parsed ParsedJson is not a valid JSON.
*`size_t get_depth() const`: returns the current depth (start at 1 with 0 reserved for the fictitious root node)
*`int8_t get_scope_type() const`: a scope is a series of nodes at the same depth, typically it is either an object (`{`) or an array (`[`). The root node has type 'r'.
*`bool move_forward()`: move forward in document order
*`uint8_t get_type() const`: retrieve the character code of what we're looking at: `[{"slutfn` are the possibilities
*`int64_t get_integer() const`: get the int64_t value at this node; valid only if get_type() is "l"
*`uint64_t get_unsigned_integer() const`: get the value as uint64; valid only if get_type() is "u"
*`const char *get_string() const`: get the string value at this node (NULL ended); valid only if get_type() is ", note that tabs, and line endings are escaped in the returned value, return value is valid UTF-8, it may contain NULL chars, get_string_length() determines the true string length.
*`uint32_t get_string_length() const`: return the length of the string in bytes
*`double get_double() const`: get the double value at this node; valid only if gettype() is "d"
*`bool is_unsigned_integer() const`: Returns true if the current type of node is an unsigned integer. You can get its value with `get_unsigned_integer()`. Only a large value, which is out of range of a 64-bit signed integer, is represented internally as an unsigned node. On the other hand, a typical positive integer, such as 1, 42, or 1000000, is as a signed node. Be aware this function returns false for a signed node.
*`bool is_double() const`: self-explanatory
*`bool is_number() const`: self-explanatory
*`bool is_true() const`: self-explanatory
*`bool is_false() const`: self-explanatory
*`bool is_null() const`: self-explanatory
*`bool is_number() const`: self-explanatory
*`bool move_to_key(const char *key)`: when at {, go one level deep, looking for a given key, if successful, we are left pointing at the value, if not, we are still pointing at the object ({) (in case of repeated keys, this only finds the first one). We seek the key using C's strcmp so if your JSON strings contain NULL chars, this would trigger a false positive: if you expect that to be the case, take extra precautions. Furthermore, we do the comparison character-by-character without taking into account Unicode equivalence.
*`bool move_to_key_insensitive(const char *key)`: as above, but case insensitive lookup
*`bool move_to_key(const char *key, uint32_t length)`: as above except that the target can contain NULL characters
*`void move_to_value()`: when at a key location within an object, this moves to the accompanying, value (located next to it). This is equivalent but much faster than calling `next()`.
*`bool move_to_index(uint32_t index)`: when at `[`, go one level deep, and advance to the given index, if successful, we are left pointing at the value,i f not, we are still pointing at the array
*`bool move_to(const char *pointer, uint32_t length)`: Moves the iterator to the value correspoding to the json pointer. Always search from the root of the document. If successful, we are left pointing at the value, if not, we are still pointing the same value we were pointing before the call. The json pointer follows the rfc6901 standard's syntax: https://tools.ietf.org/html/rfc6901
*`bool move_to(const std::string &pointer) `: same as above but with a std::string parameter
*`bool next()`: Withing a given scope (series of nodes at the same depth within either an array or an object), we move forward. Thus, given [true, null, {"a":1}, [1,2]], we would visit true, null, { and [. At the object ({) or at the array ([), you can issue a "down" to visit their content. valid if we're not at the end of a scope (returns true).
*`bool prev()`: Within a given scope (series of nodes at the same depth within either an
array or an object), we move backward.
*`bool up()`: moves back to either the containing array or object (type { or [) from within a contained scope.
*`bool down()`: moves us to start of that deeper scope if it not empty. Thus, given [true, null, {"a":1}, [1,2]], if we are at the { node, we would move to the "a" node.
*`void to_start_scope()`: move us to the start of our current scope, a scope is a series of nodes at the same level
*`void rewind()`: repeatedly calls up until we are at the root of the document
*`bool print(std::ostream &os, bool escape_strings = true) const`: print the node we are currently pointing at
> A JSON parser transforms a JSON text into another representation. A JSON parser MUST accept all texts that conform to the JSON grammar. A JSON parser MAY accept non-JSON forms or extensions. An implementation may set limits on the size of texts that it accepts. An implementation may set limits on the maximum depth of nesting. An implementation may set limits on the range and precision of numbers. An implementation may set limits on the length and character contents of strings.
> All JSON is Javascript but NOT all Javascript is JSON. So {property:1} is invalid because property does not have double quotes around it. {'property':1} is also invalid, because it's single quoted while the only thing that can placate the JSON specification is double quoting. JSON is even fussy enough that {"property":.1} is invalid too, because you should have of course written {"property":0.1}. Also, don't even think about having comments or semicolons, you guessed it: they're invalid. (credit:https://github.com/elzr/vim-json)
- Lu, Yifan, et al. "Tree structured data processing on GPUs." Cloud Computing, Data Science & Engineering-Confluence, 2017 7th International Conference on. IEEE, 2017.
- Sidhu, Reetinder. "High throughput, tree automata based XML processing using FPGAs." Field-Programmable Technology (FPT), 2013 International Conference on. IEEE, 2013.
- Dai, Zefu, Nick Ni, and Jianwen Zhu. "A 1 cycle-per-byte XML parsing accelerator." Proceedings of the 18th annual ACM/SIGDA international symposium on Field programmable gate arrays. ACM, 2010.
- Lin, Dan, et al. "Parabix: Boosting the efficiency of text processing on commodity processors." High Performance Computer Architecture (HPCA), 2012 IEEE 18th International Symposium on. IEEE, 2012. http://parabix.costar.sfu.ca/export/1783/docs/HPCA2012/final_ieee/final.pdf
- Deshmukh, V. M., and G. R. Bamnote. "An empirical evaluation of optimization parameters in XML parsing for performance enhancement." Computer, Communication and Control (IC4), 2015 International Conference on. IEEE, 2015.
- Moussalli, Roger, et al. "Efficient XML Path Filtering Using GPUs." ADMS@ VLDB. 2011.
- Jianliang, Ma, et al. "Parallel speculative dom-based XML parser." High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC-ICESS), 2012 IEEE 14th International Conference on. IEEE, 2012.
- Li, Y., Katsipoulakis, N.R., Chandramouli, B., Goldstein, J. and Kossmann, D., 2017. Mison: a fast JSON parser for data analytics. Proceedings of the VLDB Endowment, 10(10), pp.1118-1129. http://www.vldb.org/pvldb/vol10/p1118-li.pdf
- Cameron, Robert D., et al. "Parallel scanning with bitstream addition: An xml case study." European Conference on Parallel Processing. Springer, Berlin, Heidelberg, 2011.
- Cameron, Robert D., Kenneth S. Herdy, and Dan Lin. "High performance XML parsing using parallel bit stream technology." Proceedings of the 2008 conference of the center for advanced studies on collaborative research: meeting of minds. ACM, 2008.
- Shah, Bhavik, et al. "A data parallel algorithm for XML DOM parsing." International XML Database Symposium. Springer, Berlin, Heidelberg, 2009.
- Cameron, Robert D., and Dan Lin. "Architectural support for SWAR text processing with parallel bit streams: the inductive doubling principle." ACM Sigplan Notices. Vol. 44. No. 3. ACM, 2009.
- Amagasa, Toshiyuki, Mana Seino, and Hiroyuki Kitagawa. "Energy-Efficient XML Stream Processing through Element-Skipping Parsing." Database and Expert Systems Applications (DEXA), 2013 24th International Workshop on. IEEE, 2013.
- Medforth, Nigel Woodland. "icXML: Accelerating Xerces-C 3.1. 1 using the Parabix Framework." (2013).
- Zhang, Qiang Scott. Embedding Parallel Bit Stream Technology Into Expat. Diss. Simon Fraser University, 2010.
- Cameron, Robert D., et al. "Fast Regular Expression Matching with Bit-parallel Data Streams."
- Lin, Dan. Bits filter: a high-performance multiple string pattern matching algorithm for malware detection. Diss. School of Computing Science-Simon Fraser University, 2010.
- Yang, Shiyang. Validation of XML Document Based on Parallel Bit Stream Technology. Diss. Applied Sciences: School of Computing Science, 2013.
